HEL-543: add data hub observability side-channel (provider status, source catalog, lineage)
- New provider_call_log/provider_health tables (additive-only schema), wired via a fail-open observability.observe()/record_call() helper. - Tushare pipeline keeps its existing src_calls record unchanged and now also feeds the unified provider_health/provider_call_log side channel. - Eastmoney/Tencent realtime_serve.py call sites and the iFinD steward call site are wrapped with observability.observe() at the call site only; no adapter internals, routing, fallback order, or return values are touched. - New read-only admin API endpoints: /admin/api/providers/status, /admin/api/source-catalog, /admin/api/lineage, /admin/api/lineage/affected. - New static, read-only source_catalog.py and lineage.py registries documenting existing providers/interfaces/datasets and known main-site consumers (cited against backend/features/screener and backend/features/heaven call sites). - provider_call_log is purged by the existing pipeline.cleanup() job alongside src_calls/job_runs. - 47 new unit/integration tests covering classification, fail-open behavior under DB/log failures, unchanged payloads/exceptions on success and failure paths, and the new HTTP endpoints. Full suite: 173 tests, all green. Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: multica-agent <github@multica.ai>
This commit is contained in:
总工
co-authored by
Cursor
multica-agent
Cursor
multica-agent
parent
4a90c32fcc
commit
ad70d8fccc
@@ -0,0 +1,145 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import tempfile
|
||||
import threading
|
||||
import unittest
|
||||
from http.server import ThreadingHTTPServer
|
||||
from pathlib import Path
|
||||
from urllib.request import Request, urlopen
|
||||
|
||||
from datahub.adapters.tushare import TushareAdapter
|
||||
from datahub.crypto import SecretVault
|
||||
from datahub.httpapp import make_handler
|
||||
from datahub.hub import Hub
|
||||
from datahub.settings import Settings
|
||||
from tests.fixtures import TRADE_DATE, fake_transport
|
||||
|
||||
|
||||
class AdminObservabilityApiTests(unittest.TestCase):
|
||||
"""HEL-543: new read-only admin endpoints for provider status, source
|
||||
catalog and lineage. These must never require write access and must
|
||||
never touch the existing routing/publish logic."""
|
||||
|
||||
def setUp(self) -> None:
|
||||
self.tmp = tempfile.TemporaryDirectory()
|
||||
settings = Settings(
|
||||
encryption_key=SecretVault.generate_key(),
|
||||
api_token="z" * 32,
|
||||
admin_password="StartPass1",
|
||||
tushare_token="real-tushare-token-abcdef",
|
||||
db_path=Path(self.tmp.name) / "hub.db",
|
||||
scheduler_enabled=False,
|
||||
)
|
||||
self.hub = Hub(settings, adapter=TushareAdapter("real-tushare-token-abcdef", transport=fake_transport))
|
||||
handler = make_handler(self.hub)
|
||||
self.server = ThreadingHTTPServer(("127.0.0.1", 0), handler)
|
||||
threading.Thread(target=self.server.serve_forever, daemon=True).start()
|
||||
self.base = f"http://127.0.0.1:{self.server.server_address[1]}"
|
||||
|
||||
_, body, cookie_header = self._json(
|
||||
"/admin/api/login", "POST", {"username": "hub_admin", "password": "StartPass1"}
|
||||
)
|
||||
cookie = cookie_header.split(";")[0]
|
||||
csrf = body["csrf"]
|
||||
self._json(
|
||||
"/admin/api/change-password",
|
||||
"POST",
|
||||
{"current": "StartPass1", "new_password": "NewPass123"},
|
||||
cookie=cookie,
|
||||
csrf=csrf,
|
||||
)
|
||||
self.cookie = cookie
|
||||
self.csrf = csrf
|
||||
|
||||
def tearDown(self) -> None:
|
||||
self.server.shutdown()
|
||||
self.server.server_close()
|
||||
self.tmp.cleanup()
|
||||
|
||||
def _json(self, path, method="GET", body=None, cookie="", csrf=""):
|
||||
data = None if body is None else json.dumps(body).encode()
|
||||
headers = {"Content-Type": "application/json"}
|
||||
if cookie:
|
||||
headers["Cookie"] = cookie
|
||||
if csrf:
|
||||
headers["X-CSRF-Token"] = csrf
|
||||
req = Request(self.base + path, data=data, headers=headers, method=method)
|
||||
with urlopen(req, timeout=5) as resp:
|
||||
set_cookie = resp.headers.get("Set-Cookie", "")
|
||||
return resp.status, json.loads(resp.read().decode()), set_cookie
|
||||
|
||||
def _get(self, path):
|
||||
return self._json(path, cookie=self.cookie, csrf=self.csrf)
|
||||
|
||||
def test_providers_status_reflects_real_pipeline_activity(self) -> None:
|
||||
pipeline = self.hub.pipeline
|
||||
pipeline.ingest_reference(TRADE_DATE)
|
||||
pipeline.run_dataset("daily", TRADE_DATE)
|
||||
|
||||
status, body, _ = self._get("/admin/api/providers/status")
|
||||
self.assertEqual(status, 200)
|
||||
health = body["health"]
|
||||
self.assertTrue(any(item["provider"] == "tushare" and item["interface"] == "daily" for item in health))
|
||||
row = next(item for item in health if item["provider"] == "tushare" and item["interface"] == "daily")
|
||||
self.assertEqual(row["state"], "ok")
|
||||
recent = body["recent_calls"]
|
||||
self.assertTrue(any(item["provider"] == "tushare" and item["interface"] == "daily" for item in recent))
|
||||
|
||||
def test_providers_status_filters_by_provider(self) -> None:
|
||||
pipeline = self.hub.pipeline
|
||||
pipeline.ingest_reference(TRADE_DATE)
|
||||
pipeline.run_dataset("daily", TRADE_DATE)
|
||||
|
||||
status, body, _ = self._get("/admin/api/providers/status?provider=tushare")
|
||||
self.assertEqual(status, 200)
|
||||
self.assertTrue(all(item["provider"] == "tushare" for item in body["health"]))
|
||||
self.assertTrue(all(item["provider"] == "tushare" for item in body["recent_calls"]))
|
||||
|
||||
status, body, _ = self._get("/admin/api/providers/status?provider=eastmoney")
|
||||
self.assertEqual(status, 200)
|
||||
self.assertEqual(body["health"], [])
|
||||
self.assertEqual(body["recent_calls"], [])
|
||||
|
||||
def test_source_catalog_lists_known_providers_without_leaking_secrets(self) -> None:
|
||||
status, body, _ = self._get("/admin/api/source-catalog")
|
||||
self.assertEqual(status, 200)
|
||||
blob = json.dumps(body)
|
||||
self.assertNotIn("real-tushare-token-abcdef", blob)
|
||||
providers = {item["provider"] for item in body["items"]}
|
||||
self.assertIn("tushare", providers)
|
||||
self.assertIn("eastmoney", providers)
|
||||
self.assertIn("tencent", providers)
|
||||
self.assertIn("ifind", providers)
|
||||
|
||||
def test_lineage_snapshot_and_affected_query(self) -> None:
|
||||
status, body, _ = self._get("/admin/api/lineage")
|
||||
self.assertEqual(status, 200)
|
||||
self.assertTrue(len(body["items"]) > 0)
|
||||
datasets = {item["dataset"] for item in body["items"]}
|
||||
self.assertIn("stocks", datasets)
|
||||
|
||||
status, body, _ = self._get("/admin/api/lineage/affected?provider=tushare&interface=daily")
|
||||
self.assertEqual(status, 200)
|
||||
self.assertEqual(body["provider"], "tushare")
|
||||
self.assertEqual(body["interface"], "daily")
|
||||
|
||||
def test_must_change_password_blocks_new_endpoints_too(self) -> None:
|
||||
from urllib.error import HTTPError
|
||||
|
||||
_, body, cookie_header = self._json(
|
||||
"/admin/api/login", "POST", {"username": "hub_admin", "password": "NewPass123"}
|
||||
)
|
||||
# Freshly logged-in user has already changed password in setUp, so
|
||||
# this login should not require a change; verify the endpoint is
|
||||
# reachable with a valid, non-must-change session (regression guard
|
||||
# against accidentally bypassing the must-change gate for these new
|
||||
# routes).
|
||||
cookie = cookie_header.split(";")[0]
|
||||
csrf = body["csrf"]
|
||||
status, _, _ = self._json("/admin/api/source-catalog", cookie=cookie, csrf=csrf)
|
||||
self.assertEqual(status, 200)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
Reference in New Issue
Block a user